-
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Dockerfile
232 lines (183 loc) · 8.74 KB
/
Dockerfile
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
# The vLLM Dockerfile is used to construct vLLM image that can be directly used
# to run the OpenAI compatible server.
# Please update any changes made here to
# docs/source/dev/dockerfile/dockerfile.rst and
# docs/source/assets/dev/dockerfile-stages-dependency.png
ARG CUDA_VERSION=12.4.1
#################### BASE BUILD IMAGE ####################
# prepare basic build environment
FROM nvidia/cuda:${CUDA_VERSION}-devel-ubuntu20.04 AS base
ARG CUDA_VERSION=12.4.1
ARG PYTHON_VERSION=3.10
ENV DEBIAN_FRONTEND=noninteractive
RUN echo 'tzdata tzdata/Areas select America' | debconf-set-selections \
&& echo 'tzdata tzdata/Zones/America select Los_Angeles' | debconf-set-selections \
&& apt-get update -y \
&& apt-get install -y ccache software-properties-common \
&& add-apt-repository ppa:deadsnakes/ppa \
&& apt-get update -y \
&& apt-get install -y python${PYTHON_VERSION} python${PYTHON_VERSION}-dev python${PYTHON_VERSION}-venv \
&& if [ "${PYTHON_VERSION}" != "3" ]; then update-alternatives --install /usr/bin/python3 python3 /usr/bin/python${PYTHON_VERSION} 1; fi \
&& python3 --version
RUN apt-get update -y \
&& apt-get install -y git curl sudo
# Install pip s.t. it will be compatible with our PYTHON_VERSION
RUN curl -sS https://bootstrap.pypa.io/get-pip.py | python${PYTHON_VERSION}
RUN python3 -m pip --version
# Workaround for https://github.com/openai/triton/issues/2507 and
# https://github.com/pytorch/pytorch/issues/107960 -- hopefully
# this won't be needed for future versions of this docker image
# or future versions of triton.
RUN ldconfig /usr/local/cuda-$(echo $CUDA_VERSION | cut -d. -f1,2)/compat/
WORKDIR /workspace
# install build and runtime dependencies
COPY requirements-common.txt requirements-common.txt
COPY requirements-adag.txt requirements-adag.txt
COPY requirements-cuda.txt requirements-cuda.txt
RUN --mount=type=cache,target=/root/.cache/pip \
python3 -m pip install -r requirements-cuda.txt
COPY requirements-mamba.txt requirements-mamba.txt
RUN python3 -m pip install packaging
RUN python3 -m pip install -r requirements-mamba.txt
# cuda arch list used by torch
# can be useful for both `dev` and `test`
# explicitly set the list to avoid issues with torch 2.2
# see https://github.com/pytorch/pytorch/pull/123243
ARG torch_cuda_arch_list='7.0 7.5 8.0 8.6 8.9 9.0+PTX'
ENV TORCH_CUDA_ARCH_LIST=${torch_cuda_arch_list}
#################### BASE BUILD IMAGE ####################
#################### WHEEL BUILD IMAGE ####################
FROM base AS build
ARG PYTHON_VERSION=3.10
# install build dependencies
COPY requirements-build.txt requirements-build.txt
RUN --mount=type=cache,target=/root/.cache/pip \
python3 -m pip install -r requirements-build.txt
# install compiler cache to speed up compilation leveraging local or remote caching
RUN apt-get update -y && apt-get install -y ccache
# files and directories related to build wheels
COPY csrc csrc
COPY setup.py setup.py
COPY cmake cmake
COPY CMakeLists.txt CMakeLists.txt
COPY requirements-common.txt requirements-common.txt
COPY requirements-adag.txt requirements-adag.txt
COPY requirements-cuda.txt requirements-cuda.txt
COPY pyproject.toml pyproject.toml
COPY vllm vllm
# max jobs used by Ninja to build extensions
ARG max_jobs=2
ENV MAX_JOBS=${max_jobs}
# number of threads used by nvcc
ARG nvcc_threads=8
ENV NVCC_THREADS=$nvcc_threads
ARG buildkite_commit
ENV BUILDKITE_COMMIT=${buildkite_commit}
ARG USE_SCCACHE
# if USE_SCCACHE is set, use sccache to speed up compilation
RUN --mount=type=cache,target=/root/.cache/pip \
if [ "$USE_SCCACHE" = "1" ]; then \
echo "Installing sccache..." \
&& curl -L -o sccache.tar.gz https://github.com/mozilla/sccache/releases/download/v0.8.1/sccache-v0.8.1-x86_64-unknown-linux-musl.tar.gz \
&& tar -xzf sccache.tar.gz \
&& sudo mv sccache-v0.8.1-x86_64-unknown-linux-musl/sccache /usr/bin/sccache \
&& rm -rf sccache.tar.gz sccache-v0.8.1-x86_64-unknown-linux-musl \
&& if [ "$CUDA_VERSION" = "11.8.0" ]; then \
export SCCACHE_BUCKET=vllm-build-sccache-2; \
else \
export SCCACHE_BUCKET=vllm-build-sccache; \
fi \
&& export SCCACHE_REGION=us-west-2 \
&& export CMAKE_BUILD_TYPE=Release \
&& sccache --show-stats \
&& python3 setup.py bdist_wheel --dist-dir=dist --py-limited-api=cp38 \
&& sccache --show-stats; \
fi
ENV CCACHE_DIR=/root/.cache/ccache
RUN --mount=type=cache,target=/root/.cache/ccache \
--mount=type=cache,target=/root/.cache/pip \
if [ "$USE_SCCACHE" != "1" ]; then \
python3 setup.py bdist_wheel --dist-dir=dist --py-limited-api=cp38; \
fi
# check the size of the wheel, we cannot upload wheels larger than 100MB
COPY .buildkite/check-wheel-size.py check-wheel-size.py
RUN python3 check-wheel-size.py dist
#################### EXTENSION Build IMAGE ####################
#################### DEV IMAGE ####################
FROM base as dev
COPY requirements-lint.txt requirements-lint.txt
COPY requirements-test.txt requirements-test.txt
COPY requirements-dev.txt requirements-dev.txt
RUN --mount=type=cache,target=/root/.cache/pip \
python3 -m pip install -r requirements-dev.txt
#################### DEV IMAGE ####################
#################### MAMBA Build IMAGE ####################
FROM dev as mamba-builder
# max jobs used for build
ARG max_jobs=2
ENV MAX_JOBS=${max_jobs}
WORKDIR /usr/src/mamba
COPY requirements-mamba.txt requirements-mamba.txt
# Download the wheel or build it if a pre-compiled release doesn't exist
RUN pip --verbose wheel -r requirements-mamba.txt \
--no-build-isolation --no-deps --no-cache-dir
#################### MAMBA Build IMAGE ####################
#################### vLLM installation IMAGE ####################
# image with vLLM installed
FROM nvidia/cuda:${CUDA_VERSION}-base-ubuntu20.04 AS vllm-base
ARG CUDA_VERSION=12.4.1
ARG PYTHON_VERSION=3.10
WORKDIR /vllm-workspace
RUN echo 'tzdata tzdata/Areas select America' | debconf-set-selections \
&& echo 'tzdata tzdata/Zones/America select Los_Angeles' | debconf-set-selections \
&& apt-get update -y \
&& apt-get install -y ccache software-properties-common \
&& add-apt-repository ppa:deadsnakes/ppa \
&& apt-get update -y \
&& apt-get install -y python${PYTHON_VERSION} python${PYTHON_VERSION}-dev python${PYTHON_VERSION}-venv \
&& if [ "${PYTHON_VERSION}" != "3" ]; then update-alternatives --install /usr/bin/python3 python3 /usr/bin/python${PYTHON_VERSION} 1; fi \
&& python3 --version
RUN apt-get update -y \
&& apt-get install -y python3-pip git vim curl libibverbs-dev
# Install pip s.t. it will be compatible with our PYTHON_VERSION
RUN curl -sS https://bootstrap.pypa.io/get-pip.py | python${PYTHON_VERSION}
RUN python3 -m pip --version
# Workaround for https://github.com/openai/triton/issues/2507 and
# https://github.com/pytorch/pytorch/issues/107960 -- hopefully
# this won't be needed for future versions of this docker image
# or future versions of triton.
RUN ldconfig /usr/local/cuda-$(echo $CUDA_VERSION | cut -d. -f1,2)/compat/
# install vllm wheel first, so that torch etc will be installed
RUN --mount=type=bind,from=build,src=/workspace/dist,target=/vllm-workspace/dist \
--mount=type=cache,target=/root/.cache/pip \
python3 -m pip install dist/*.whl --verbose
RUN --mount=type=bind,from=mamba-builder,src=/usr/src/mamba,target=/usr/src/mamba \
--mount=type=cache,target=/root/.cache/pip \
python3 -m pip install /usr/src/mamba/*.whl --no-cache-dir
RUN --mount=type=cache,target=/root/.cache/pip \
python3 -m pip install https://github.com/flashinfer-ai/flashinfer/releases/download/v0.1.2/flashinfer-0.1.2+cu121torch2.4-cp310-cp310-linux_x86_64.whl
#################### vLLM installation IMAGE ####################
#################### TEST IMAGE ####################
# image to run unit testing suite
# note that this uses vllm installed by `pip`
FROM vllm-base AS test
ADD . /vllm-workspace/
# install development dependencies (for testing)
RUN --mount=type=cache,target=/root/.cache/pip \
python3 -m pip install -r requirements-dev.txt
# doc requires source code
# we hide them inside `test_docs/` , so that this source code
# will not be imported by other tests
RUN mkdir test_docs
RUN mv docs test_docs/
RUN mv vllm test_docs/
#################### TEST IMAGE ####################
#################### OPENAI API SERVER ####################
# openai api server alternative
FROM vllm-base AS vllm-openai
# install additional dependencies for openai api server
RUN --mount=type=cache,target=/root/.cache/pip \
pip install accelerate hf_transfer 'modelscope!=1.15.0'
ENV VLLM_USAGE_SOURCE production-docker-image
ENTRYPOINT ["python3", "-m", "vllm.entrypoints.openai.api_server"]
#################### OPENAI API SERVER ####################